Detecting apparatus, detection method, and program

a detection method and detection method technology, applied in the direction of mechanical measuring arrangements, instruments, using mechanical means, etc., can solve the problems of difficult to accurately detect the anomaly, difficult to detect the anomaly through a spectral analysis of a predetermined frequency,

Active Publication Date: 2016-03-17
IBM CORP
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0004]In one embodiment, a detecting apparatus for detecting one or more anomalies of an operating body that periodically operates is disclosed. The detecting apparatus comprises a processor that is communicatively coupled to a dividing unit, a model learning unit, a difference calculating unit, and an anomaly detecting unit. The dividing unit divides a data sequence acquired through detection of an operation of the operating body into a plurality of divided data sequences in a time direction. The model learning unit learns e...

Problems solved by technology

Moreover, since the spectrum signal also has an individual difference, it has been difficult to detect the anomaly through a spectral analysis of a predetermined frequency or the like.
Even further, unlike an ideal bright-line spectrum it has been difficult ...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Detecting apparatus, detection method, and program
  • Detecting apparatus, detection method, and program
  • Detecting apparatus, detection method, and program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021]While the present invention will be described below through one or more embodiments, the following embodiment is not intended to limit the disclosure according to the claims. Moreover, all combinations of features described in the embodiment are not necessarily essential for solutions in the invention.

[0022]FIG. 1 illustrates a configuration example of a detecting apparatus 100 according to this embodiment. The detecting apparatus 100, through learning, predicts time-series data to be obtained in the case of an normal operation of an operating body or the like that periodically operates, based on a time-series detection signal detected in response to an operation of the operating body, and detects anomaly of the operating body, depending on a difference component between a predicted model component and the detection signal.

[0023]Here, the operating body repeats a periodic operation, such as vibration, for a certain period of time. Moreover, the operating body may include a rot...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Provided is a detecting apparatus for detecting one or more anomalies of an operating body. The detecting apparatus includes a processor communicatively coupled to a dividing unit, a model learning unit, a difference calculating unit, and an anomaly detecting unit. The dividing unit divides a data sequence corresponding to an operation of the operating body into a plurality of divided data sequences in a time direction. The model learning unit learns each of the plurality of divided data sequences according to a regression model in the time direction, and calculates a model component modeling each of the divided data sequences. The difference calculating unit calculates a difference component indicating a difference between each of the plurality of divided data sequences and their corresponding model component. The anomaly detecting unit detects one or more anomalies of the operating body based on the calculated difference components.

Description

BACKGROUND[0001]The present invention relates to a detecting apparatus, a detection method, and a program.[0002]Traditionally known detection of an anomaly in an operating body or the like that periodically operates has been performed by detecting vibration or the like in response to an operation of the operating body, transforming detected time-series data into frequency data, and analyzing a frequency spectrum. See, for example, Patent Literatures JP2013-30015A and JP2011-59790A.[0003]However, a spectrum signal indicating a normal operation of the operating body or the like may change over time in signal strength and a generated frequency due to, for example, an implementation state of the operating body, a surrounding environment such as temperature, and a physical change caused by abrasion or the like. Moreover, since the spectrum signal also has an individual difference, it has been difficult to detect the anomaly through a spectral analysis of a predetermined frequency or the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01M13/04G01H1/00G06N20/00
CPCG01M13/045G06N99/005G01H1/003G06N20/00G06N5/00G06N5/04G01M13/02G06N7/01
Inventor TAKAHASHI, TOSHIHIRO
Owner IBM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products